Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1916 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.8219. Min Act: -0.0001

Data Index: 1540196 (Python Code)

Max Activating Token Index: 759

Text #1

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7996. Min Act: -0.0001

Data Index: 1615698 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7777. Min Act: -0.0001

Data Index: 1422888 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7339. Min Act: -0.0001

Data Index: 1527247 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7411. Min Act: -0.0001

Data Index: 1622376 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7587. Min Act: -0.0001

Data Index: 1637893 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.8307. Min Act: -0.0001

Data Index: 1633210 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7691. Min Act: -0.0001

Data Index: 1397390 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7631. Min Act: -0.0001

Data Index: 1499994 (Python Code)

Max Activating Token Index: 754

Text #9

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7555. Min Act: -0.0001

Data Index: 1605381 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1514623 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7264. Min Act: -0.0001

Data Index: 961189 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7443. Min Act: -0.0001

Data Index: 717663 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6869. Min Act: -0.0001

Data Index: 1558972 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7473. Min Act: -0.0001

Data Index: 675218 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7816. Min Act: -0.0001

Data Index: 1500663 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.8191. Min Act: -0.0001

Data Index: 1621871 (Python Code)

Max Activating Token Index: 675

Text #17

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7241. Min Act: -0.0001

Data Index: 304192 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7596. Min Act: -0.0001

Data Index: 1148188 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6995. Min Act: -0.0001

Data Index: 1588053 (Python Code)

Max Activating Token Index: 628